INDEX

Explanations

terms related to documentation and records, particularly in the context of entomology and scientific classifications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Part of scientific/catalog names: abbreviations and Latin names

np_acts-logits-general · gemini-2.0-flash

modus vivendi, nova, evidence, case

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-2.33

 Jefus

-2.22

 itſelf

-2.22

 pleaſure

-2.19

 purpoſe

-2.19

 Monfieur

-2.07

Efq

-2.06

 houſe

-2.04

 raiſ

-2.00

 themſelves

-2.00

POSITIVE LOGITS

et

0.68

pra

0.52

ex

0.52

0.49

ae

0.48

ad

0.47

Om

0.46

 plus

0.45

Activations Density 0.229%

terms related to documentation and records, particularly in the context of entomology and scientific classifications

Part of scientific/catalog names: abbreviations and Latin names

modus vivendi, nova, evidence, case

No Comments

No Known Activations